SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu
{"title":"SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space","authors":"Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu","doi":"10.48550/arXiv.2206.01867","DOIUrl":null,"url":null,"abstract":"We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.","PeriodicalId":211605,"journal":{"name":"International Conference on Smart Multimedia","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Smart Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2206.01867","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
SPGNet:基于空间投影的低维空间三维人体姿态估计
我们提出了一种将多维重投影与监督学习相结合的三维人体姿态估计方法SPGNet。在该方法中,2d -to-3D提升网络预测三维人体姿态的全局位置和坐标。然后,我们将估计的3D姿态连同空间调整一起重新投影回2D关键点。损失函数将估计的三维姿态与三维姿态地面真值进行比较,并将重新投影的二维姿态与输入的二维姿态进行比较。此外,我们提出了一个运动学约束,以限制预测目标恒定的人骨长度。基于对Human3.6M数据集的估计结果,我们的方法在定性和定量上都优于许多最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space Matrix Syncer - A Multi-chain Data Aggregator For Supporting Blockchain-based Metaverses Product Re-identification System in Fully Automated Defect Detection RCA-NET: Image Recovery Network with Channel Attention Group for Image Dehazing Tissue Discrimination Through Force-Feedback from Impedance Spectroscopy in Robot-Assisted Surgery
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1